© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66137
    Prev
    Next
    INDEX
    Explanations

    other alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    っていて
    -0.98
     zarówno
    -0.97
     REALLY
    -0.92
     "}";
    -0.90
    あんまり
    -0.88
    álny
    -0.86
     såsom
    -0.86
     dezelfde
    -0.85
    ্য
    -0.85
    тила
    -0.85
    POSITIVE LOGITS
     other
    1.80
    อื่น
    1.24
     outros
    1.14
     lainnya
    1.12
     سایر
    1.05
     других
    1.05
     diğer
    1.02
     otros
    1.02
    其它
    1.01
    ictions
    1.00
    Activations Density 0.089%

    No Known Activations